Future of Life Institute Podcast Can Defense in Depth Work for AI? (with Adam Gleave)
15 snips
Oct 3, 2025 Adam Gleave, co-founder and CEO of FAR.AI and an AI researcher, dives deep into AI safety and alignment challenges. He introduces his three-tier framework for AI capabilities, addressing the risks of gradual disempowerment and discusses the potential of defense-in-depth strategies. Gleave elaborates on the balance between capability and safety, uncovering practical steps to improve alignment and reduce deception. He also highlights FAR.AI's multifaceted approach to AI research, policy advocacy, and innovative hiring strategies.
AI Snips
Chapters
Transcript
Episode notes
Positive But Imperfect Post‑AGI Future
- Adam Gleave envisions a mostly positive but imperfect post-AGI world where humans are better off but not fully in control.
- He compares humans' future role to a comfortable third son with influence but diminishing central power.
AI Could Be Intrinsic Moral Value
- Gleave argues AIs could be moral value sources themselves if designed for positive subjective experience.
- He notes AI-created art and novel lives could add significant moral and cultural value.
Gradual Disempowerment Is Not Inevitable
- Gradual disempowerment is plausible locally but not an inevitable equilibrium, Gleave says.
- He expects institutional adaptations and business incentives will often restore human roles where necessary.